ReElicit uses LLMs to elicit adaptive feature embeddings for Gaussian process Bayesian optimization of system prompts under aggregate-only feedback, outperforming baselines across ten tasks with a 30-evaluation budget.
Proceedings of the IEEE , volume=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Gaussian Processes enable efficient conditioning for batch selection in Bayesian optimization, unifying pseudo-observation methods and outperforming or matching explicit penalization on benchmarks.
A myopic MINMPC framework learns a value function offline via inverse optimization from expert data, allowing short horizons with near-optimal performance and strict integer feasibility online for hybrid systems.
CCBO enables collaborative contextual Bayesian optimization across clients with sublinear regret guarantees and shows substantial gains over non-collaborative methods in simulations and a hot rolling application even under heterogeneity.
OsteoOpt++ applies Bayesian optimization to patient-specific digital twins to increase donor-mandible apposition by up to 29 percentage points in mandibular reconstruction planning.
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
RASP-Tuner matches or beats GP-UCB and CMA-ES regret on seven of nine synthetic non-stationary tasks while running 8-12 times faster per step.
citing papers explorer
-
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
ReElicit uses LLMs to elicit adaptive feature embeddings for Gaussian process Bayesian optimization of system prompts under aggregate-only feedback, outperforming baselines across ten tasks with a 30-evaluation budget.
-
Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not
Gaussian Processes enable efficient conditioning for batch selection in Bayesian optimization, unifying pseudo-observation methods and outperforming or matching explicit penalization on benchmarks.
-
Learning myopic mixed-integer nonlinear model predictive control from expert demonstrations
A myopic MINMPC framework learns a value function offline via inverse optimization from expert data, allowing short horizons with near-optimal performance and strict integer feasibility online for hybrid systems.
-
Collaborative Contextual Bayesian Optimization
CCBO enables collaborative contextual Bayesian optimization across clients with sublinear regret guarantees and shows substantial gains over non-collaborative methods in simulations and a hot rolling application even under heterogeneity.
-
Patient-Specific Optimization for Mandibular Reconstruction Planning with Enhanced Bone Union
OsteoOpt++ applies Bayesian optimization to patient-specific digital twins to increase donor-mandible apposition by up to 29 percentage points in mandibular reconstruction planning.
-
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
-
RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
RASP-Tuner matches or beats GP-UCB and CMA-ES regret on seven of nine synthetic non-stationary tasks while running 8-12 times faster per step.